Role OverviewAI Safety Expert - Red Teamer will conduct jailbreaks, prompt injections, and bias exploitation on conversational AI models and agents. They will also generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
What You Will Do
The main day-to-day responsibilities will include red teaming, generating human data, applying structure using taxonomies and benchmarks, documenting reproducibly, and reviewing AI outputs on sensitive topics.
Why It Might Be a Fit
To be a fit for this role, you should have prior experience in red teaming, AI adversarial work, or cybersecurity, and be able to explain risks clearly to both technical and non-technical stakeholders.
Requirements
- Fluent in English and Vietnamese
- Prior experience in red teaming, AI adversarial work, or cybersecurity
- Ability to explain risks clearly to both technical and non-technical stakeholders
Benefits
]]>